Eye examination instrument and instruction pushing method and system thereof

Abstract

The invention provides an eye examination instrument and an instruction pushing method and system thereof, and the method comprises the steps: constructing a semantic model which comprises a reference eye item, a reference eye state, a reference motion identifier, a reference character identifier and a corresponding relation between a reference operation motion, obtaining the motion of a current to-be-examined object, and pushing the motion to the current to-be-examined object; the method comprises the following steps: acquiring voice of a current to-be-inspected object, acquiring an eye state and an eye item of the current to-be-inspected object, extracting an action identifier in an action, performing character conversion on the voice, extracting a character identifier matched with a preset character in the converted character, and obtaining a semantic model according to the action identifier, the eye state, the eye item, the character identifier and the semantic model. And obtaining an operation action and sending an operation instruction corresponding to the operation action to the eye examination instrument. And inputting the action identifier, the eye state, the eye item and the character identifier into a semantic model to obtain an operation action, so that the eye examination instrument automatically examines the current to-be-detected object based on the operation action.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of examination instruments, in particular to an eye examination instrument and an instruction pushing method and system thereof. BACKGROUND

[0002] The traditional process of ophthalmic examination usually relies on professional operators to use electronic instruments to obtain expected data by adjusting parameters one by one. Although this process is standardized and systematic, it often takes a long time and human resources. In the prior art, even if a patient wears a professional electronic instrument, he or she cannot operate it by himself or herself, so as to improve the convenience and efficiency of the examination. SUMMARY

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide an eye examination instrument and an instruction pushing method and system thereof, which solve the problem that in the prior art, even if a patient wears a professional electronic instrument, he or she cannot operate it by himself or herself.

[0004] According to one aspect of the present application, an instruction pushing method based on an eye examination instrument is provided, comprising:

[0005] constructing a semantic model; wherein the semantic model comprises a corresponding relationship between a reference eye item, a reference eye state, a reference action identifier, a reference text identifier and a reference operation action;

[0006] obtaining an action of a current object to be examined;

[0007] obtaining a voice of the current object to be examined;

[0008] obtaining an eye state and an eye item of the current object to be examined;

[0009] extracting an action identifier in the action;

[0010] converting the voice into text and extracting a text identifier in the converted text that matches a preset text;

[0011] obtaining an operation action according to the action identifier, the eye state, the eye item, the text identifier and the semantic model, and sending the operation action to an eye examination instrument.

[0012] In an embodiment, the constructing a semantic model comprises:

[0013] obtaining a plurality of reference operation actions of an eye examination instrument;

[0014] determining a reference eye item corresponding to each reference operation action;

[0015] determining a reference eye state corresponding to each reference eye item;

[0016] acquiring reference actions and reference voices of a plurality of reference objects;

[0017] extracting reference action identifiers in the reference actions of each reference object;

[0018] extracting reference word identifiers in the reference voices of each reference object;

[0019] determining target action identifiers and target word identifiers corresponding to different reference eye objects;

[0020] assigning reference action identifiers matching the target action identifiers to the reference eye objects corresponding to the target action identifiers;

[0021] assigning reference word identifiers matching the target word identifiers to the reference eye objects corresponding to the target word identifiers;

[0022] constructing a semantic model according to the plurality of reference eye objects, the plurality of reference operation actions, the plurality of eye states, the plurality of reference action identifiers, and the plurality of reference word identifiers.

[0023] In an embodiment, the extracting of the reference action identifiers in the reference actions of each reference object comprises:

[0024] extracting the number of same actions in the reference actions of each reference object; wherein the reference action identifier comprises the number of same actions.

[0025] In an embodiment, the extracting of the reference action identifiers in the reference actions of each reference object comprises:

[0026] extracting action trajectories in the reference actions of each reference object; wherein the reference action identifier comprises the action trajectory.

[0027] In an embodiment, the sending of the operation instruction corresponding to the operation action to the eye examination instrument comprises:

[0028] if the operation action is multiple, determining the probability of same actions in the multiple operation actions;

[0029] if the probability of same actions is greater than a first preset probability, sending the operation instruction corresponding to the same actions to the eye examination instrument.

[0030] In an embodiment, the sending of the operation instruction corresponding to the operation action to the eye examination instrument comprises:

[0031] if the operation action is multiple, determining eye levels corresponding to the eye states; wherein each eye level represents the severity of the eye state;

[0032] select an operation action conforming to the eye level from the operation actions as a first target operation action;

[0033] send an operation instruction corresponding to the first target operation action to the eye examination instrument.

[0034] In an embodiment, the sending of the operation instruction corresponding to the operation action to the eye examination instrument comprises:

[0035] acquire identity information of the current object to be examined;

[0036] according to the identity information, find a historical examination record of the current object to be examined;

[0037] if the operation action in the historical examination record is the same as the operation action, acquire a historical action identifier and a historical text identifier corresponding to the operation action in the historical examination record;

[0038] acquire other operation actions containing the historical action identifier and the historical text identifier;

[0039] send an operation instruction corresponding to the other operation actions to the eye examination instrument.

[0040] In an embodiment, the sending of the operation instruction corresponding to the operation action to the eye examination instrument comprises:

[0041] if the operation action is multiple, acquire a probability value between the operation action and the action identifier, the eye state, the eye item, and the text identifier;

[0042] select an operation action with a probability value greater than a second preset probability as a second target operation action;

[0043] send an operation instruction corresponding to the second target operation action to the eye examination instrument.

[0044] According to another aspect of the present application, there is provided an instruction pushing system based on an eye examination instrument, comprising:

[0045] a semantic model construction module for constructing a semantic model; wherein the semantic model comprises a corresponding relationship between a reference eye item, a reference eye state, a reference action identifier, a reference text identifier, and a reference operation action;

[0046] a tactile sensing module for acquiring an action of a current object to be examined; and extracting an action identifier in the action;

[0047] an auditory sensing module for acquiring a voice of a current object to be examined; and converting the voice into text and extracting a text identifier matching a preset text in the converted text;

[0048] an eye tracking analysis module, configured to acquire an eye state and an eye item of a current object to be examined;

[0049] a conveying and generating module, configured to acquire an operation action according to the action identifier, the eye state, the eye item, the text identifier and the semantic model, and send an operation instruction corresponding to the operation action to the eye examination instrument.

[0050] According to another aspect of the present application, an eye examination instrument is provided, comprising the instruction pushing system based on the eye examination instrument.

[0051] The eye examination instrument and the instruction pushing method and system thereof provided by the present application comprise: constructing a semantic model, wherein the semantic model comprises a corresponding relationship between a reference eye item, a reference eye state, a reference action identifier, a reference text identifier and a reference operation action; acquiring an action of a current object to be examined; acquiring a voice of the current object to be examined; acquiring an eye state and an eye item of the current object to be examined; extracting an action identifier in the action; converting the voice into text and extracting a text identifier in the converted text that matches a preset text; acquiring an operation action according to the action identifier, the eye state, the eye item, the text identifier and the semantic model, and sending an operation instruction corresponding to the operation action to the eye examination instrument. By inputting the action identifier, the eye state, the eye item and the text identifier into the semantic model, the operation action is outputted, and the operation instruction corresponding to the operation action is sent to the eye examination instrument, so that the eye examination instrument can examine the eye of the current object to be examined, and the current object to be examined can be self-examined without the operation of a professional, thereby improving the examination efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0052] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of embodiments of the present application and constitute a part of the specification, which together with the description, serve to explain the present application. The drawings are not intended to limit the present application, and in the drawings, like reference numerals refer to like elements or steps throughout.

[0053] Figure 1 is a flowchart of an instruction pushing method based on an eye examination instrument provided by an exemplary embodiment of the present application.

[0054] Figure 2 is a flowchart of an operation action sending method provided by an exemplary embodiment of the present application.

[0055] Figure 3is a flowchart of an operation action sending method provided by another example embodiment of the present application.

[0056] Figure 4 is a structural diagram of an instruction pushing system based on an eye examination instrument provided by an example embodiment of the present application.

[0057] Figure 5 is a structural diagram of an instruction pushing system based on an eye examination instrument provided by another example embodiment of the present application.

[0058] Figure 6 is a structural diagram of an electronic device provided by an example embodiment of the present application. DETAILED DESCRIPTION

[0059] In the following, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the described example embodiments.

[0060] Figure 1 is a flowchart of an instruction pushing method based on an eye examination instrument provided by an example embodiment of the present application. As shown in Figure 1 the instruction pushing method based on an eye examination instrument includes:

[0061] Step 110: constructing a semantic model, wherein the semantic model includes a corresponding relationship between a reference eye item, a reference eye state, a reference action identifier, a reference text identifier and a reference operation action.

[0062] In the embodiments of the present application, the reference eye item refers to various elements related to the eye, such as eye anatomy, visual function, eye disease, etc., wherein the eye anatomy can include eyeball, cornea, iris, pupil, etc. The visual function includes color vision, visual acuity, visual field, etc. The eye disease includes cataract, glaucoma, macular degeneration, etc. The reference eye state can include normal state, abnormal state and disease state, etc. The normal state includes eye health, normal vision, etc. The abnormal state includes dry eye, blurred vision, eye fatigue, etc. The disease state includes the symptom manifestation of specific eye diseases, etc. The reference action identifier can include fixation, blinking, following, reading, etc., wherein fixation means that the eye concentrates on a certain target. Blinking means the rapid closing and opening of the eyelid. Following means the action of the eye tracking a moving object. Reading means the process of the eye moving along the text. The reference text identifier includes retinal detachment, refractive error, etc. The reference operation action includes vision examination, fundus examination, use of eye drops, eye cleaning, regular review, etc.

[0063] For example, when the reference eye state is determined to be an abnormal state, the reference eye item is determined to be an eye film examination, the reference action identifier is determined to be blinking, and the reference text identifier is determined to be blepharitis, the corresponding reference operation action can be to use artificial tears.

[0064] Step 120: Obtain the action of the current object to be examined.

[0065] In the embodiment of the present application, when the object to be detected wears an ophthalmic examination instrument, the action of the object to be examined can be obtained. For example, a slight finger tapping signal or a foot tapping signal of the current object, and the like. Specifically, a camera is installed on the ophthalmic examination instrument, which can track the action of the object to be examined in real time. Alternatively, an accelerometer and a gyroscope sensor are installed on the ophthalmic examination instrument, thereby capturing the motion and posture change of the body.

[0066] Step 130: Obtain the voice of the current object to be examined.

[0067] In the embodiment of the present application, when the object to be detected emits a voice, the voice can be collected and stored. Specifically, a microphone can be installed on the ophthalmic examination instrument, and the voice of the object to be detected is collected through the microphone.

[0068] Step 140: Obtain the eye state and eye item of the current object to be examined.

[0069] In the embodiment of the present application, the eye state of the object to be examined can be identified through the camera, so as to determine whether the eye state of the object to be examined is abnormal. The eye item is input into the ophthalmic examination instrument, so as to determine the eye item made by the object to be examined.

[0070] Step 150: Extract the action identifier in the action.

[0071] In the embodiment of the present application, when the action identifier in the action is extracted, the specific features and semantics of each action need to be determined first. For example, when a person waves his hand, the action identifier can include the frequency and duration of waving the hand.

[0072] Step 160: Convert the voice into text and extract the text identifier matching the preset text from the converted text.

[0073] In the embodiment of the present application, since the voice emitted by the object to be detected is detected, the voice can be converted into a piece of text, and the text identifier matching the preset text can be selected from the piece of text. For example, the voice is I want to turn on the camera, and the preset text is “turn on” and “camera”. Then the text identifier is “turn on” and “camera”.

[0074] Step 170: obtaining an operation action according to the action identifier, the eye state, the eye item, the character identifier and the semantic model, and sending an operation instruction corresponding to the operation action to the eye examination instrument.

[0075] In the embodiment of the present application, the eye examination instrument operates based on the operation instruction and generates a cooperation instruction which is sent to the object to be detected through voice broadcast. Alternatively, the eye examination instrument generates a cooperation instruction or a notification in the process of operation and sends it to the object to be detected, so that the object to be detected performs corresponding actions according to the cooperation instruction or the notification.

[0076] The instruction pushing method of the eye examination instrument provided in the present application comprises: constructing a semantic model, wherein the semantic model comprises a corresponding relationship between a reference eye item, a reference eye state, a reference action identifier, a reference character identifier and a reference operation action; obtaining an action of a current object to be examined; obtaining a voice of the current object to be examined; obtaining an eye state and an eye item of the current object to be examined; extracting an action identifier in the action; converting the voice into characters and extracting a character identifier in the converted characters which matches a preset character; obtaining an operation action according to the action identifier, the eye state, the eye item, the character identifier and the semantic model, and sending an operation instruction corresponding to the operation action to the eye examination instrument. By inputting the action identifier, the eye state, the eye item and the character identifier into the semantic model, the operation action is outputted, and the operation instruction corresponding to the operation action is sent to the eye examination instrument, so that the eye examination instrument examines the eye of the current object to be detected, thereby enabling the current object to be detected to perform self-examination without the operation of a professional, and further improving the efficiency of examination.

[0077] In an embodiment, step 110 can be specifically implemented as: obtaining a plurality of reference operation actions of the eye examination instrument; determining a reference eye item corresponding to each reference operation action; determining a reference eye state corresponding to each reference eye item; obtaining a reference action and a reference voice of a plurality of reference objects; extracting a reference action identifier in the reference action of each reference object; extracting a reference character identifier in the reference voice of each reference object; determining a target action identifier and a target character identifier corresponding to different reference eye items; assigning a reference action identifier matching the target action identifier to the reference eye item corresponding to the target action identifier; assigning a reference character identifier matching the target character identifier to the reference eye item corresponding to the target character identifier; and constructing a semantic model according to the plurality of reference eye items, the plurality of reference operation actions, the plurality of eye states, the plurality of reference action identifiers and the plurality of reference character identifiers.

[0078] In the embodiment of the present application, in order to quickly determine the operation action of the to-be-detected object, a semantic model can be constructed, and the corresponding operation action is obtained by inputting the eye identifier, eye state, eye item and text identifier into the semantic model, and the ophthalmic examination device performs the operation action indicated by the operation action.

[0079] Specifically, a plurality of reference operation actions of the eye examination instrument are obtained, a reference eye item corresponding to each reference operation action is determined, a reference eye state corresponding to each reference eye item is determined, a reference action and a reference voice of a plurality of reference objects are obtained, a reference action identifier in the reference action of each reference object is extracted, a reference text identifier in the reference voice of each reference object is extracted, a target action identifier and a target text identifier corresponding to different reference eye items are determined, a reference action identifier matched with the target action identifier is assigned to the reference eye item corresponding to the target action identifier, a reference text identifier matched with the target text identifier is assigned to the reference eye item corresponding to the target text identifier, and a semantic model is constructed according to the plurality of reference eye items, the plurality of reference operation actions, the plurality of eye states, the plurality of reference action identifiers and the plurality of reference text identifiers.

[0080] The reference eye item refers to various elements related to the eye, such as eye anatomy, visual function, eye disease, etc. The eye anatomy can include eyeball, cornea, iris, pupil, etc. The visual function includes color vision, vision, visual field, etc. The eye disease includes cataract, glaucoma, macular degeneration, etc. The reference eye state can include normal state, abnormal state and disease state, etc. The normal state includes eye health, normal vision, etc. The abnormal state includes dry eye, blurred vision, eye fatigue, etc. The disease state includes symptoms of specific eye diseases, etc. The reference action identifier can include fixation, blinking, following, reading, etc. The fixation means that the eye concentrates on a certain target. The blinking means the rapid closing and opening of the eyelid. The following means the action of the eye tracking a moving object. The reading means the process of the eye moving along the text. The reference text identifier includes retinal detachment, ametropia, etc. The reference operation action includes vision examination, fundus examination, use of eye drops, eye cleaning, regular review, etc. The operation action in the present application can be obtained by referring to the operation instruction material.

[0081] In an embodiment, step 110 can be specifically implemented as: extracting the number of same actions in the reference action of each reference object; wherein the reference action identifier includes the number of same actions.

[0082] In the embodiments of the present application, when extracting the number of the same actions in the reference actions of each reference object, first, systematic action recognition and classification need to be performed on each reference object. Each type of reference action identification can be quantified by analyzing its features, duration and frequency. For example, if a reference object performs the action of "waving hands" within a period of time, the number of occurrences of the action can be recorded and identified as "waving hands: 3 times".

[0083] In an embodiment, step 110 can be specifically implemented as: extracting action trajectories in the reference actions of each reference object; wherein the reference action identification comprises the action trajectories.

[0084] In the embodiments of the present application, when extracting the action trajectories in the reference actions of each reference object, the spatial and temporal dimensions of the action need to be comprehensively analyzed. Action trajectory refers to the path of the object moving in space when performing a specific action. By using sensors (such as accelerometers and gyroscopes) or computer vision technology, the position changes of various key points of the object when performing the action can be accurately recorded. For example, when a person stretches out his hand to grab an object, the action trajectory will include the dynamic path of the wrist, elbow and shoulder, as well as the movement trajectory of these points in three-dimensional space. We can convert these trajectory data into visual graphics to help analyze the smoothness, speed and direction change of the action.

[0085] In an embodiment, step 110 can be specifically implemented as: determining the number of occurrences of a specific reference action in the reference actions of each reference object within a preset time period; calculating the frequency of the specific reference action according to the preset time period and the number of occurrences of the specific reference action; wherein the reference action identification comprises the frequency of the specific reference action.

[0086] In the embodiments of the present application, the frequency of an action refers to the number of occurrences of a specific action within a certain time period, which is a way to quantify action activities and is used to analyze the behavior patterns of individuals or objects. Action frequency can determine the regularity, intensity and trend of a specific behavior. For example, determine the time range of observation (such as 1 minute, 1 hour, etc.), record the number of occurrences of a specific action within the time period, and divide the total number of actions by the length of the time period to obtain the frequency per unit time. For example, if a certain action occurs 10 times in 5 minutes, the frequency is 2 times / minute.

[0087] Figure 2 is a flowchart of the operation action sending method provided by an exemplary embodiment of the present application. As shown in Figure 2 , step 170 can include:

[0088] Step 171: If the operation action is multiple, determine the probability of the same action in the multiple operation actions.

[0089] In the embodiment of the present application, when the operation actions output by the semantic model are multiple, the operation actions output by the semantic model can include operation actions corresponding to other eye items due to the abnormal eye state, and therefore, in order to accurately obtain the operation actions, the probabilities of the same actions in the multiple operation actions can be determined. For example, the operation actions include opening a light point, following a light point, opening a light point, following a light point, and keeping eyes still. Then, it can be obtained that the opening of the light point accounts for a high proportion in the multiple operation actions, and the following of the light point accounts for a high proportion in the multiple operation actions.

[0090] Step 172: If the probability of the same action is greater than the first preset probability, operation instructions corresponding to the same action are sent to the eye examination instrument.

[0091] In the embodiment of the present application, once it is confirmed that the probability of the same action exceeds the first preset probability, the operation instructions corresponding to the same action with high probability are sent to the eye examination instrument, thereby improving the accuracy of eye examination, and ensuring that the detection equipment only responds to possible abnormalities or specific needs, thereby improving the efficiency and effectiveness of detection.

[0092] Figure 3 is a flowchart of an operation action sending method provided by another exemplary embodiment of the present application. As shown in Figure 3 Step 170 can include:

[0093] Step 173: If the operation actions are multiple, an eye level corresponding to the eye state is determined, wherein each eye level represents the severity of the eye state.

[0094] In the embodiment of the present application, by determining the eye level corresponding to the eye state of the current object to be detected, necessary operation actions are preferentially executed, and the object to be detected can be quickly examined. Since the eye state of the object to be detected is very serious, if the operation actions are more and each operation action needs to be executed, the eye state can be exacerbated, and therefore, the eye level corresponding to the eye state needs to be determined, so as to determine which operation steps are preferentially executed, thereby quickly determining the reason causing the abnormality of the eye.

[0095] The eye level of the eye state can include A, B and C, the level of A is greater than the level of B, and the level of B is greater than the level of C.

[0096] Step 174: Selecting, as a first target operation action, an operation action conforming to the eye level from the multiple operation actions.

[0097] In the embodiment of the present application, different eye grades represent different severity of eye conditions, therefore, the operation action conforming to the eye grade is selected from the plurality of operation actions to be performed preferentially, so as to quickly check the cause and make the eye of the object to be detected can be quickly relieved.

[0098] Step 175: sending the operation instruction corresponding to the first target operation action to the eye examination instrument.

[0099] In an embodiment, step 170 can be specifically implemented as: obtaining the identity information of the object to be examined; searching the historical examination record of the object to be examined according to the identity information; if the operation action in the historical examination record is the same as the operation action, obtaining the historical action identifier and the historical text identifier corresponding to the operation action in the historical examination record; obtaining other operation actions containing the historical action identifier and the historical text identifier; and sending the operation instruction corresponding to the other operation actions to the eye examination instrument.

[0100] In the embodiment of the present application, the identity information of the object to be examined can be determined by face recognition through the camera and other devices. The historical examination record of the object to be examined can be searched from the database through the identity information. The historical examination record of the object to be examined can be obtained to know the historical state of the eye of the object to be examined and the solution in advance. However, if the operation action in the plurality of historical examination records is the same as the operation action in the semantic model, it may indicate that the operation action output by the semantic model may not be able to solve the eye problem of the object to be examined. Therefore, the historical action identifier and the historical text identifier corresponding to the operation action in the historical examination record can be obtained, the operation instruction corresponding to the other operation actions can be obtained through the historical action identifier and the historical text identifier, and the eye examination instrument can be triggered to examine the eye of the object to be detected through the operation instruction corresponding to the other operation actions.

[0101] In an embodiment, step 170 can be specifically implemented as: if the operation action is a plurality of operation actions, obtaining the probability value between the operation action and the action identifier, the eye state, the eye item and the text identifier; selecting the operation action with the probability value greater than the second preset probability as the second target operation action; and sending the operation instruction corresponding to the second target operation action to the eye examination instrument.

[0102] In the embodiment of the present application, since the operation action is caused by the action identifier, the eye state, the eye item, and the character identifier input semantic model, the operation action can be multiple. Therefore, which operation action is input to the eye examination instrument can be determined by the probability value between the operation action and the action identifier, the eye state, the eye item, and the character identifier. When the action identifier, the eye state, the eye item, and the character identifier are input to the semantic model, the result output by the semantic model can not be unique. Therefore, it is necessary to determine which operation step has greater relevance with the action identifier, the eye state, the eye item, and the character identifier. Therefore, the operation action with the probability value greater than the second preset probability can be set as the target operation action by setting the second preset probability, and the operation instruction corresponding to the target operation action is sent to the eye examination instrument.

[0103] Figure 4 is a structural schematic diagram of an instruction pushing system based on an eye examination instrument provided by an exemplary embodiment of the present application. As shown in Figure 4 the instruction pushing system based on the eye examination instrument includes a semantic model construction module 201 for constructing a semantic model; wherein the semantic model includes the corresponding relationship between the reference eye item, the reference eye state, the reference action identifier, the reference character identifier, and the reference operation action; a tactile sensing module 202 for acquiring the action of the current object to be examined; extracting the action identifier in the action; an auditory sensing module 203 for acquiring the voice of the current object to be examined; converting the voice into characters and extracting the character identifier matched with the preset character in the converted characters; an eye tracking analysis module 204 for acquiring the eye state and the eye item of the current object to be examined; a communication and generation module 205 for acquiring the operation action according to the action identifier, the eye state, the eye item, the character identifier, and the semantic model, and sending the operation instruction corresponding to the operation action to the eye examination instrument.

[0104] The application provides an eye examination instrument instruction pushing system, which comprises a semantic model construction module, a touch sensing module, an auditory sensing module, an eye tracking analysis module and a communication and generation module.

[0105] Figure 5 is a structural schematic diagram of an eye examination instrument-based instruction pushing system provided by another exemplary embodiment of the application. Figure 5 As shown in the figure, the semantic model construction module 201 can be specifically configured to: acquire a plurality of reference operation actions of the eye examination instrument; determine a reference eye examination item corresponding to each reference operation action; determine a reference eye state corresponding to each reference eye examination item; acquire reference actions and reference voices of a plurality of reference objects; extract a reference action identifier in the reference action of each reference object; extract a reference text identifier in the reference voice of each reference object; determine a target action identifier and a target text identifier corresponding to different reference eye examination items; assign a reference action identifier matched with the target action identifier to the reference eye examination item corresponding to the target action identifier; assign a reference text identifier matched with the target text identifier to the reference eye examination item corresponding to the target text identifier; and construct a semantic model according to the plurality of reference eye examination items, the plurality of reference operation actions, the plurality of eye states, the plurality of reference action identifiers and the plurality of reference text identifiers.

[0106] In an embodiment, the semantic model construction module 201 can be specifically configured to: extract the number of same actions in the reference action of each reference object; and wherein the reference action identifier comprises the number of same actions.

[0107] In an embodiment, the semantic model construction module 201 can be specifically configured to: extract an action trajectory in the reference action of each reference object; and wherein the reference action identifier comprises the action trajectory.

[0108] In one embodiment, the communication and generation module 205 may be specifically configured to: if there are multiple operation actions, determine the probability of the same action among the multiple operation actions; if the probability of the same action is greater than a first preset probability, send the operation instruction corresponding to the same action to the eye examination instrument.

[0109] In one embodiment, the communication and generation module 205 may include: a determining unit 2051, configured to determine the eye level corresponding to the eye state if there are multiple operation actions; wherein each eye level represents the severity of the eye state; a selecting unit 2052, configured to select an operation action that matches the eye level from the multiple operation actions as the first target operation action; and a sending unit 2053, configured to send the operation instruction corresponding to the first target operation action to the eye examination instrument.

[0110] In one embodiment, the communication and generation module 205 may be specifically configured to: obtain the identity information of the object to be inspected; search for the historical inspection records of the object to be inspected based on the identity information; if the operation action in the historical inspection record is the same as the operation action, obtain the historical action identifier and historical text identifier corresponding to the operation action in the historical inspection record; obtain other operation actions containing the historical action identifier and historical text identifier; and send the operation instructions corresponding to the other operation actions to the eye examination instrument.

[0111] In one embodiment, the communication and generation module 205 may be specifically configured as follows: if there are multiple operation actions, obtain the probability values ​​between the operation action and the action identifier, eye state, eye item, and text identifier; select the operation action with a probability value greater than the second preset probability as the second target operation action; and send the operation instruction corresponding to the second target operation action to the eye examination instrument.

[0112] This application provides an eye examination instrument, including: a command push system based on the aforementioned eye examination instrument.

[0113] Figure 6 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0114] like Figure 6 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0115] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0116] The memory 12 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, which the processor 11 can execute to implement the instruction pushing method based on an eye examination instrument of various embodiments of the present application and / or other desired functions described above. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0117] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0118] When the electronic device 10 is a stand-alone device, the input device 13 can be a communication network connector for receiving the acquired input signals from the first device and the second device.

[0119] In addition, the input device 13 can further include, for example, a keyboard, a mouse, and the like.

[0120] The output device 14 can output various information including the determined distance information, direction information, and the like to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0121] Of course, in order to simplify, Figure 6 In FIG. 1, only some of the components related to the present application among the components of the electronic device 10 are illustrated, and components such as a bus, an input / output interface, and the like are omitted. In addition to this, the electronic device 10 can further include any other appropriate components according to a specific application.

[0122] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, and the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote cloud device or server.

[0123] The computer readable storage medium can be any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] The foregoing description has been presented for the purposes of illustration and description. Furthermore, the description is not intended to limit the embodiments of the application to the form disclosed herein. Although various example aspects and embodiments have been discussed above, those of ordinary skill in the art will appreciate a variety of modifications, alternatives, permutations, additions, and sub-combinations of the described aspects and embodiments.

Claims

1. A method for pushing instructions based on an eye examination instrument, characterized in that, include: Construct a semantic model; wherein the semantic model includes the correspondence between reference eye items, reference eye states, reference action identifiers, reference text identifiers, and reference operation actions; Get the current action of the object to be inspected; Get the speech of the object to be inspected; Obtain the current eye status and eye items of the object to be inspected; Extract the action identifier from the action; The speech is converted into text, and the text identifiers that match the preset text are extracted from the converted text. Based on the action identifier, the eye state, the eye items, the text identifier, and the semantic model, the operation action is obtained and the operation instruction corresponding to the operation action is sent to the eye examination instrument.

2. The instruction push method based on an eye examination instrument according to claim 1, characterized in that, The construction of the semantic model includes: Obtain multiple reference operating actions of the eye examination instrument; Identify the corresponding reference eye item for each reference operation; Determine the reference eye condition corresponding to each reference eye item; Acquire reference actions and reference speech from multiple reference objects; Extract the reference motion identifier from the reference motion of each reference object; Extract the reference text identifier from the reference speech of each reference object; Determine the target action icons and target text icons corresponding to different reference eye items; Assign a reference action identifier that matches the target action identifier to the reference eye item corresponding to the target action identifier; Assign reference text identifiers that match the target text identifier to the reference eye item corresponding to the target text identifier; A semantic model is constructed based on multiple reference eye items, multiple reference operation actions, multiple eye states, multiple reference action identifiers, and multiple reference text identifiers.

3. The instruction push method based on an eye examination instrument according to claim 2, characterized in that, The extraction of reference action identifiers from the reference actions of each reference object includes: Extract the number of identical actions in the reference actions of each reference object; wherein, the reference action identifier includes the number of identical actions.

4. The instruction push method based on an eye examination instrument according to claim 2, characterized in that, The extraction of reference action identifiers from the reference actions of each reference object includes: Extract the motion trajectory from the reference motion of each reference object; wherein, the reference motion identifier includes the motion trajectory.

5. The instruction push method based on an eye examination instrument according to claim 1, characterized in that, Sending the operation command corresponding to the operation action to the eye examination instrument includes: If there are multiple operations, then determine the probability of the same operation among the multiple operations; If the probability of the same action is greater than the first preset probability, then the same action is sent to the eye examination instrument.

6. The instruction push method based on an eye examination instrument according to claim 1, characterized in that, Sending the operation command corresponding to the operation action to the eye examination instrument includes: If there are multiple operations, then the eye level corresponding to the eye condition is determined; wherein, each eye level represents the severity of the eye condition. Select the operation action that matches the eye level from multiple operation actions as the first target operation action; The operation command corresponding to the first target operation action is sent to the eye examination instrument.

7. The instruction push method based on an eye examination instrument according to claim 1, characterized in that, Sending the operation command corresponding to the operation action to the eye examination instrument includes: Obtain the identity information of the object to be inspected; Based on the identity information, retrieve the historical inspection records of the object to be detected. If the operation action in the historical inspection record is the same as the operation action, then obtain the historical action identifier and historical text identifier corresponding to the operation action in the historical inspection record; Obtain other operation actions containing the historical action identifier and the historical text identifier; The operation instructions corresponding to the other operation actions are sent to the eye examination instrument.

8. The instruction push method based on an eye examination instrument according to claim 1, characterized in that, Sending the operation command corresponding to the operation action to the eye examination instrument includes: If there are multiple operation actions, then obtain the probability values ​​between the operation action and the action identifier, the eye state, the eye item, and the text identifier; The operation action whose probability value is greater than the second preset probability is selected as the second target operation action; The operation command corresponding to the second target operation action is sent to the eye examination instrument.

9. A command push system based on an eye examination instrument, characterized in that, include: A semantic model construction module is used to construct a semantic model; wherein, the semantic model includes reference eye items, reference eye states, reference action identifiers, and the correspondence between reference text identifiers and reference operation actions; The tactile sensing module is used to acquire the movement of the object to be inspected and extract the movement identifier from the movement. An auditory sensing module is used to acquire the speech of the object to be inspected; convert the speech into text and extract the text identifiers that match the preset text from the converted text; The eye tracking analysis module is used to obtain the current eye status and eye items of the object to be inspected; The communication and generation module is used to obtain the operation action based on the action identifier, the eye state, the eye item, the text identifier and the semantic model, and send the operation instruction corresponding to the operation action to the eye examination instrument.

10. An eye examination instrument, characterized in that, include: The system includes the instruction push system based on an eye examination instrument as described in claim 9.

Images